INDEX

Explanations

mentions of the geographical location "Ontario"

oai_token-act-pair · gpt-3.5-turbo

mentions of the location Ontario

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ·ãĥ£

-0.94

ãĥķ

-0.92

gers

-0.89

ãĥĭ

-0.84

bler

-0.81

ging

-0.80

geist

-0.80

Ö¼

-0.77

ê

-0.77

ebus

-0.76

POSITIVE LOGITS

 Provincial

1.06

 Ontario

1.01

 Pradesh

0.92

 Canada

0.87

 provincial

0.82

 unemploy

0.79

 province

0.77

Canada

0.75

 Centre

0.74

 Superior

0.73

Activations Density 0.007%

mentions of the geographical location "Ontario"

mentions of the location Ontario

No Comments

No Known Activations